Europe
ToBeamOrNotToBeam
This is a much harder setting than for continuous tasks, which enjoy gradient flows from discriminators to generators, usually leading to dramatic learning instabilities. However,weclaim thatthiscanbesolvedbymaking discriminator and generator networks cooperate to produce output sequences during training.
Retrospective Adversarial Replay for Continual Learning
To avoid these problems, this paper proposes a method, "Retrospective Adversarial
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
This dataset includes over 3.5 million documents with rich metadata, making it one of the most extensive collections of debate evidence.
Joint-task Self-supervised Learning for Temporal Correspondence
Xueting Li, Sifei Liu, Shalini De Mello, Xiaolong Wang, Jan Kautz, Ming-Hsuan Yang
Neural Information Processing Systems http://nips.cc/
Artistic Style Transfer with Internal-external Learning and Contrastive Learning
Although existing artistic style transfer methods have achieved significant improvement with deep neural networks, they still suffer from artifacts such as disharmonious colors and repetitive patterns. Motivated by this, we propose an internal-external style transfer method with two contrastive losses.
Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
Offline safe reinforcement learning (RL) aims to find an optimal policy using a pre-collected dataset when data collection is impractical or risky.
MonteCarloTreeSearchbasedVariableSelection forHighDimensionalBayesianOptimization
Our regret bound generalizes that of GP-UCB [38] which always selects all variables, aswellasthatofDropout [21]whichselectsdvariables randomly ineachiteration.
Probabilistic Logic Neural Networks for Reasoning
Neural Information Processing Systems http://nips.cc/